khanrc/pt.darts issues and pull requests

#46 - Compression ready

Pull Request - State: closed - Opened by MattPoyser about 2 years ago

#45 - what does the "auxiliary_head" mean?

Issue - State: open - Opened by Sameul-kaji over 2 years ago

#44 - how to use the visualize.py

Issue - State: open - Opened by try-gx almost 3 years ago - 1 comment

#43 - Hessian computation issue (seems like there is a bug)

Issue - State: open - Opened by MartinXPN over 3 years ago

#42 - How to train own dataset!

Issue - State: open - Opened by Kirito-520 over 3 years ago - 1 comment

#41 - Questions about DARTS

Issue - State: open - Opened by buttercutter over 3 years ago

#40 - batch_size issue

Issue - State: open - Opened by buttercutter over 3 years ago - 2 comments

#39 - Run augment.py and out of memory after one epoch

Issue - State: open - Opened by weihui98 about 4 years ago

#38 - Error in deriving the final genotype

Issue - State: open - Opened by xiangzhluo over 4 years ago

#37 - nothing happens after running search.py

Issue - State: open - Opened by yudabi over 4 years ago - 1 comment

#36 - low test accuracy in FashionMNIST

Issue - State: open - Opened by Liang-yc over 4 years ago

#35 - Does anyone meet the problem of memory leak? I trained this code on my own dataset and found that the memory keep rising during training, and I have no idea to solve it.

Issue - State: open - Opened by ZuhaoLiu over 4 years ago

#34 - It seems that there lost a parentheses in the compute_hessian function. -- (p-n) / 2.*eps

Issue - State: open - Opened by Frizy-up over 4 years ago - 1 comment

#33 - Search Not Working?

Issue - State: open - Opened by rpand002 over 4 years ago - 4 comments

#32 - why darts only halved the image twice in the main part?

Issue - State: open - Opened by JiyueWang over 4 years ago

#31 - How to install graphviz?

Issue - State: closed - Opened by JiyueWang almost 5 years ago - 1 comment

#30 - Is there anyone who can reproduce the result ?

Issue - State: open - Opened by heartInsert almost 5 years ago

#29 - very slow in multi-gpu

Issue - State: open - Opened by YoungDav almost 5 years ago - 4 comments

#28 - result not same as REAME.md

Issue - State: open - Opened by YoungDav almost 5 years ago - 1 comment

#27 - questions on v_grads = torch.autograd.grad(loss,v_alphas+v_weights)

Issue - State: open - Opened by cholihao almost 5 years ago

#26 - Running via Google Colab

Issue - State: open - Opened by suryakumara almost 5 years ago

#25 - Is it proper to use valid_loader in both train and validation?

Issue - State: open - Opened by kamata1729 about 5 years ago - 2 comments

#24 - validate loss cannot update

Issue - State: open - Opened by Arui1 about 5 years ago - 2 comments

#23 - Suggestion for torch.backends.cudnn.benchmark = True in search process

Issue - State: open - Opened by marsggbo about 5 years ago

#22 - Search runs only for 1 iteration

Issue - State: open - Opened by IlyaTrofimov about 5 years ago - 7 comments

#21 - Could you please tell me how do you get the random search baseline

Issue - State: open - Opened by leoozy about 5 years ago

#20 - question about SearchCNN code

Issue - State: closed - Opened by Christian-lyc about 5 years ago

#19 - what's the use of augment.py

Issue - State: closed - Opened by johsnows about 5 years ago - 2 comments

#18 - featuremap size reduce in op.py FactorizedReduce function

Issue - State: open - Opened by yjump about 5 years ago

#17 - meaning of Normal and Reduce?

Issue - State: open - Opened by Damax18 about 5 years ago

#16 - Missing Softmax for Genotype selection

Issue - State: open - Opened by ghost about 5 years ago - 3 comments

#15 - Low CIFAR-100 accuracy

Issue - State: closed - Opened by 0xsamgreen over 5 years ago - 4 comments

#14 - How to train on imagenet?THX.

Issue - State: open - Opened by betterhalfwzm over 5 years ago - 1 comment

#13 - TypeError: init() got an unexpected keyword argument 'log_dir'

Issue - State: open - Opened by zjplab over 5 years ago - 1 comment

#12 - Why using broadcast for edge weights?

Issue - State: closed - Opened by zzzxxxttt over 5 years ago - 2 comments

#11 - AttributeError: 'CIFAR10' object has no attribute 'train_data'

Issue - State: open - Opened by leidaguo over 5 years ago - 5 comments

#10 - Why is the search accuracy on the CIFAR-10 dataset only 89% accuracy?

Issue - State: closed - Opened by leidaguo over 5 years ago - 2 comments

#9 - Cannot obtain the cell architecture as the reported one.

Issue - State: closed - Opened by fanglinpu over 5 years ago - 1 comment

#8 - AssertionError: can only join a child process

Issue - State: open - Opened by twangnh over 5 years ago

#7 - License

Issue - State: closed - Opened by DaStoll over 5 years ago - 2 comments

#6 - Where do I control the connections between nodes?

Issue - State: open - Opened by sunil3590 over 5 years ago - 1 comment

#5 - Augment

Issue - State: closed - Opened by TianMingChen over 5 years ago - 5 comments

#4 - Feature/optimize architect

Pull Request - State: closed - Opened by khanrc over 5 years ago

#3 - Feature/multi gpu

Pull Request - State: closed - Opened by khanrc over 5 years ago

#2 - How to use multi-gpu

Issue - State: closed - Opened by VectorYoung over 5 years ago - 5 comments

#1 - How to run the Augment

Issue - State: closed - Opened by VectorYoung over 5 years ago - 1 comment

GitHub / khanrc/pt.darts issues and pull requests